CN111242923A - Canny operator-based insulator crack detection method based on maximum entropy threshold optimization - Google Patents
Canny operator-based insulator crack detection method based on maximum entropy threshold optimization Download PDFInfo
- Publication number
- CN111242923A CN111242923A CN202010033618.3A CN202010033618A CN111242923A CN 111242923 A CN111242923 A CN 111242923A CN 202010033618 A CN202010033618 A CN 202010033618A CN 111242923 A CN111242923 A CN 111242923A
- Authority
- CN
- China
- Prior art keywords
- insulator
- image
- maximum entropy
- crack detection
- canny operator
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 239000012212 insulator Substances 0.000 title claims abstract description 134
- 238000001514 detection method Methods 0.000 title claims abstract description 24
- 238000005457 optimization Methods 0.000 title claims abstract description 12
- 238000000034 method Methods 0.000 claims abstract description 18
- 238000001914 filtration Methods 0.000 claims abstract description 8
- 230000001629 suppression Effects 0.000 claims abstract description 5
- 238000007781 pre-processing Methods 0.000 claims abstract description 4
- 238000005315 distribution function Methods 0.000 claims description 6
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 238000009413 insulation Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 239000000463 material Substances 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 description 7
- 238000011179 visual inspection Methods 0.000 description 5
- 230000011218 segmentation Effects 0.000 description 4
- 238000003708 edge detection Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000003321 amplification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000005764 inhibitory process Effects 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an insulator crack detection method based on Canny operator maximum entropy threshold optimization, which comprises the following steps: acquiring an insulator image, and preprocessing the insulator image; calculating the maximum entropy of the insulator image gray value; performing Gaussian filtering on the insulator image; calculating the gradient amplitude and direction of the insulator image; carrying out non-maximum suppression on the gradient amplitude of the insulator image; setting a high threshold and a low threshold for the insulator image, taking the maximum entropy of the gray value of the insulator image as the high threshold, and extracting the insulator edge image by adopting a Canny operator; and carrying out crack detection on the insulator edge image containing the cracks. The method can monitor the insulator in real time, reduce manpower and material resources, improve the working efficiency, greatly reduce the probability of the insulator breaking down due to the generation of cracks and ensure the safety and stability of the power grid.
Description
Technical Field
The invention belongs to the field of insulator detection, and particularly relates to a Canny operator-based insulator crack detection method based on maximum entropy threshold optimization.
Background
With the continuous acceleration of the industrialization process and the continuous improvement of the economic level in China and the continuous enhancement of the construction of the power grid, the power network is more and more complex. The working intensity of power grid maintenance corresponding to the insulator is higher and higher, and the difficulty brought to the power grid maintenance work by quickly and accurately judging the health condition of the insulator is reduced.
The insulator is exposed to the atmosphere and works in severe environments such as strong electric field, strong mechanical stress, rapid cooling and heating, wind, rain, snow and fog, chemical substance corrosion and the like for a long time, and cracks are generated on the insulator in an unavoidable way. At present, the existing insulator crack detection method mainly comprises a visual inspection method and an instrument testing method. The insulators are usually arranged on the transmission tower, the visual inspection accuracy is not high, and no matter the visual inspection or the instrument and meter testing method is adopted, the insulators need to be close to maintenance personnel, so that inconvenience is brought to maintenance work, the labor intensity of the maintenance personnel is high, and the efficiency is low.
Noise is a factor that hinders the human sense organ from understanding the received information of the source, i.e., various undesired or unwanted parts contained in the image. Firstly, noise is inevitably generated in the process of generating, transmitting and receiving an image, secondly, impurities such as dust, rain and snow and the like attached to the surface of the insulator are noise, and meanwhile, other objects such as lines, pole frames and the like around the insulator in the image are useless information which can also be regarded as noise.
Disclosure of Invention
The invention has the technical problems that in the existing insulator crack detection method, the visual inspection accuracy is not high, and whether the visual inspection or the instrument and meter test method is adopted, a maintainer needs to be close to the insulator, so that the overhauling work is inconvenient, the labor intensity of the maintainer is high, and the efficiency is low. The acquired insulator image has a large amount of noise on the background due to the position of the insulator, and the noise includes influence factors such as lines, towers and branches, dirt can be generated on the surface of the insulator due to the effects of wind, frost, snow, fog and the like, and when the traditional image recognition technology is used for detecting the edge of the insulator, the noise can seriously interfere the result and is not beneficial to detecting the cracks of the insulator.
The invention aims to solve the problems and provides an insulator crack detection method based on Canny operator maximum entropy threshold optimization, which adopts an image recognition technology, extracts an insulator edge image possibly containing cracks from the insulator image by using an improved Canny operator after the image of the insulator is collected, identifies the edge outline of the broken insulator which accords with the edge characteristics of the insulator, further confirms whether the insulator edge outline has the cracks or not, solves the problems of low efficiency and poor accuracy caused by manual visual observation, and can reduce the labor intensity of maintainers.
The technical scheme of the invention is an insulator crack detection method based on the maximum entropy threshold optimization of a Canny operator, which comprises the following steps,
step 1: acquiring an insulator image, and preprocessing the insulator image;
step 2: calculating the maximum entropy of the insulator image gray value;
and step 3: performing Gaussian filtering on the insulator image;
and 4, step 4: calculating the gradient amplitude and direction of the insulator image, and performing non-maximum suppression on the gradient amplitude;
and 5: setting a high threshold and a low threshold for the insulator image, taking the maximum entropy of the gray value of the insulator image as the high threshold, and extracting the insulator edge image by adopting a Canny operator;
step 6: and carrying out crack detection on the insulator edge image possibly containing cracks.
Further, in step 1, the insulator image is preprocessed, insulator images are subjected to rotation transformation, the center line of the insulator in the image is in the vertical direction, and the insulator is subjected to image graying, contrast enhancement and denoising in sequence, and the method comprises the following substeps,
step 1.1: graying the insulator image;
step 1.2: enhancing the contrast of the insulator image;
step 1.3: and denoising the insulator image.
Preferably, in step 1.2, the contrast of the insulator image is enhanced, the gray scale distribution function of the image before enhancement is f (x, y), the gray scale distribution range of the image pixel is [ a, b ], after the contrast of the insulator image is enhanced, the gray scale distribution range of the image pixel is [0,255], and the expression of the gray scale distribution function g (x, y) is as follows
Preferably, the insulator image is denoised by using a wiener filter.
Further, in step 6, the crack detection is performed on the insulator edge image which may contain cracks, and the method includes the following steps,
step 6.1: judging the insulator contour line which accords with the shape characteristic of the slope function in the edge curve of the edge image in the step 5, and determining an insulator region in the image;
step 6.2: and judging whether a curve spanning the adjacent umbrella skirt exists in the insulation sub-region, and if so, judging that the umbrella skirt is cracked.
In step 2, the maximum entropy of the insulator image gray value is calculated, and a two-dimensional vector formed by pixels of pixel gray value distribution and neighborhood average gray value distribution is utilized to obtain an optimal threshold when the two-dimensional measure is maximized.
And establishing a two-dimensional gray distribution graph of the image by taking the gray value of the pixel points of the insulator image as the abscissa and the area gray mean value as the ordinate. Setting a point (s, t) as a target region, namely an insulator and background region segmentation point, setting the maximum gray value of an image as L, setting the point (s, t) as a segmentation threshold, setting a region between the point (0,0) and the point (s, t) of a two-dimensional gray distribution map as a target region A, setting a region between the point (L, L) and the point (s, t) as a background region B, setting a region between the point (s,0) and the point (L, t) as a region C, setting a region between the point (0, t) and the point (s, L) as a region D, and setting the regions C and D as boundary pixel point distribution regions and noise signal distribution regions respectively;
the two-dimensional entropy of region A H (A) is as follows
Wherein
pi,jIn order to be the probability density,
ni,jthe number of pixel points with point gray of i and area gray of j;
the number of the pixel points of the insulating sub-image is NXN;
the two-dimensional entropy H (B) of the B region is as follows
Wherein
Let p in the C and D regionsi,j0 is approximately distributed; available PB＝1-PA；HB＝HL-HA＝lg(1-PA)+(HL-HA)/(1-PA) In which H isLIs a discriminant function of entropy
Discriminant function
Is calculated as follows
Threshold point of maximum entropy
Satisfies the following formula
Compared with the prior art, the invention has the beneficial effects that:
1) the method can monitor the insulator in real time, reduce manpower and material resources, improve the working efficiency, greatly reduce the probability of the insulator breaking down due to the generation of cracks and ensure the safety and stability of the power grid;
2) according to the method, the canny operator with the optimized maximum entropy threshold value is adopted, so that the influence of image noise caused by insulator dirt, background elements and the like on the insulator edge detection can be effectively reduced, and the crack detection precision is improved;
3) according to the method, after the contour region of the insulator is judged and separated by adopting the shape characteristics of the slope function according to the general characteristic of the cracks penetrating through the adjacent sheds, the curve of the narrow chain crossing the adjacent sheds in the contour region of the insulator is detected as the cracks, so that the programming is easy to realize, and the rapid detection of the cracks is realized.
Drawings
The invention is further illustrated by the following figures and examples.
Fig. 1 is a flowchart of an insulator crack detection method based on Canny operator maximum entropy threshold optimization.
Fig. 2 is a two-dimensional gray distribution diagram of an insulator image.
Fig. 3 is a schematic view of an insulator image.
Detailed Description
As shown in fig. 1-3, the method for detecting the insulator crack based on the maximum entropy threshold optimization of the Canny operator comprises the following steps:
step 1: collecting an insulator image by using an unmanned aerial vehicle, preprocessing the insulator image, performing rotary transformation on the insulator image to enable the center line of the insulator in the image to be in the vertical direction, and performing image graying, contrast enhancement and denoising in sequence;
step 1.1: graying the insulator image;
step 1.2: enhancing the contrast of the insulator image;
step 1.3: denoising the insulator image;
step 2: calculating the maximum entropy of the insulator image gray value;
and step 3: performing Gaussian filtering on the insulator image;
and 4, step 4: calculating the gradient amplitude and direction of the insulator image, and performing non-maximum suppression on the gradient amplitude;
and 5: setting a high threshold and a low threshold for the insulator image, taking the maximum entropy of the gray value of the insulator image as the high threshold, and extracting the insulator edge image by adopting a Canny operator;
step 6: carrying out crack detection on the insulator edge image containing cracks;
step 6.1: judging the insulator contour line which accords with the shape characteristic of the slope function in the edge curve of the edge image in the step 5, and determining an insulator region in the image;
step 6.2: and judging whether a curve spanning the adjacent umbrella skirt exists in the insulation sub-region, and if so, judging that the umbrella skirt is cracked.
In step 1.2, the contrast of the insulator image is enhanced, the gray scale distribution function of the image before enhancement is f (x, y), the gray scale distribution range of the image pixel is [ a, b ], after the contrast of the insulator image is enhanced, the gray scale distribution range of the image pixel is [0,255], and the expression of the gray scale distribution function g (x, y) is as follows
And denoising the insulator image by using a wiener filter. Wiener filtering is a least variance filter that is based on making f (x, y) and f (x, y) sum on the assumption that the image signal can be approximately seen as a stationary random process
Mean square error e between2Implemented by reaching a minimum criterion function, i.e.
In the formula, E is expected to be,
f (x, y) is a clear original image function after wiener filtering;
Where G (u, v) is the Fourier transform of the degenerate figureFunction, H (u, v) is a degenerate function, Sn(u, v) is a power spectrum function of the noise, Sf(u, v) is a power spectrum function of the original image,
λ is lagrange multiplier, λ is constant in the embodiment, and (u, v) are pixel point coordinates.
The wiener filter has an automatic suppression effect on noise amplification. If the transfer function H (u, v) is zero somewhere, because
Has a denominator of Sn(u,v)/SfThe (u, v) term, so no singularity occurs. In a certain frequency spectrum region, if the signal-to-noise ratio is high, the signal-to-noise ratio is high
Sn(u,v)≤Sf(u,v)
The filter effect tends to be inverse filtering.
If the signal-to-noise ratio is small, i.e.
Sn(u,v)＞＞Sf(u,v)
The filter is insensitive in performance, and the wiener filter avoids the amplification effect on noise in the process of restoring the image. The noise is effectively filtered by the image after wiener filtering, and the contrast between the foreground and the background becomes more obvious and outstanding, so that the difference between the insulator and the background can be highlighted.
In step 2, the maximum entropy of the insulator image gray value is calculated, and a two-dimensional vector formed by pixels of pixel gray value distribution and neighborhood average gray value distribution is utilized to obtain an optimal threshold when the two-dimensional measure is maximized.
As shown in fig. 2, a two-dimensional gray distribution graph of the image is established by using the gray value of the pixel point of the insulator image as the abscissa and the area gray average value as the ordinate. Setting a point (s, t) as a target region, namely an insulator and background region segmentation point, setting the maximum gray value of an image as L, setting the point (s, t) as a segmentation threshold, setting a region between the point (0,0) and the point (s, t) of a two-dimensional gray distribution map as a target region A, setting a region between the point (L, L) and the point (s, t) as a background region B, setting a region between the point (s,0) and the point (L, t) as a region C, setting a region between the point (0, t) and the point (s, L) as a region D, and setting the regions C and D as boundary pixel point distribution regions and noise signal distribution regions respectively;
the two-dimensional entropy of region A H (A) is as follows
Wherein
pi,jIn order to be the probability density,
ni,jthe number of pixel points with point gray of i and area gray of j;
the number of the pixel points of the insulating sub-image is NXN;
the two-dimensional entropy H (B) of the B region is as follows
Wherein
Let p in the C and D regionsi,j0 is approximately distributed; available PB＝1-PA；HB＝HL-HA＝lg(1-PA)+(HL-HA)/(1-PA) In which H isLIs a discriminant function of entropy
Discriminant function
Is calculated as follows
Threshold point of maximum entropy
Satisfies the following formula
The existing Canny operator, such as the Canny operator in an image edge detection improvement algorithm based on the Canny operator published in a paper published in 'Shanghai university of transportation' journal 50 of 2016 (2016), generally has the problem that the selection of the threshold of the Canny operator has no clear calculation method, and the selection of the threshold determines the final result of edge detection, so that the threshold is too low, so that many false edges and noise points can be generated in the insulator crack detection process, and the threshold is too high, so that the information of lines and cracks needing to be reserved in the insulator sub-image cannot be reserved. Aiming at the defects, the two-dimensional maximum entropy calculated in the step 2 is used as a high threshold value in double threshold values in a Canny operator, t1、t2A low threshold and a high threshold, respectively, and t is set in the embodiment2≈2t1Thereby improving the existing Canny operator.
In step 3, the input image of the Gaussian filter is f (x, y), the Gaussian function is used for smoothing operation, and the gradient of the smoothed image g (x, y) is
The convolution operation characteristics are as follows:
wherein G (x, y) is a Gaussian function.
The image smoothing processing by adopting the Gaussian function can lead the edge of the original image to be blurred and the width to be increased, and the non-maximum value inhibition can sharpen the blurred edge.
In one embodiment, the Gaussian filter function is
Wherein σ is the standard deviation of normal distribution;
the 2 filter convolution templates of the gradient vector ▽ G are decomposed into 2 one-dimensional row and column filters by a decomposition method:
wherein k is a differential operator; and respectively using the two convolution templates for image convolution calculation to obtain output:
the method comprises the following steps of obtaining an image f (x, y), obtaining a gradient image, obtaining a point (i, j) on the image f (x, y), obtaining a difference value of an x axis, obtaining an Ey axis, obtaining a difference value of a y axis, and expressing convolution operation in an expression, wherein A (i, j) is the amplitude of the gradient and reflects the edge strength of the point (i, j) on the image f (x, y), α (i, j) is a normal vector of the point (i, j) on the image f (x, y), and is a vector orthogonal to the edge direction, namely the direction of the gradient.
The insulator is usually cracked by an isolated narrow chain intersecting the contour of the edge of the insulator, and the narrow chain penetrates through a plurality of sheds of the insulator.
In step 6.1, the ramp function adopts a ramp model disclosed in an article "Optimal Edge Detectors for RampEdges" published by IEEE Transactions on Pattern analysis and Machine understanding, 13 1991, the ramp model is as follows:
wherein epsilon is a function parameter, and appearance characteristics of most insulators can be represented by selecting a slope model with the parameter epsilon of 1.4 through analyzing each sample in the sample space.
In the embodiment, the crack detection method provided by the invention is adopted, so that the maintenance efficiency and accuracy of the power grid insulator are improved, the labor intensity of power grid maintenance personnel is reduced, and the economic loss caused by insulator faults in the power grid is reduced.
Claims (5)
1. The method for detecting the insulator cracks based on the maximum entropy threshold optimization of the Canny operator is characterized by comprising the following steps,
step 1: acquiring an insulator image, and preprocessing the insulator image;
step 2: calculating the maximum entropy of the insulator image gray value;
and step 3: performing Gaussian filtering on the insulator image;
and 4, step 4: calculating the gradient amplitude and direction of the insulator image, and performing non-maximum suppression on the gradient amplitude;
and 5: setting a high threshold and a low threshold for the insulator image, taking the maximum entropy of the gray value of the insulator image as the high threshold, and extracting the insulator edge image by adopting a Canny operator;
step 6: and carrying out crack detection on the insulator edge image possibly containing cracks.
2. The Canny operator-based insulator crack detection method based on maximum entropy threshold optimization according to claim 1, wherein in the step 1, the insulator image is preprocessed, insulator images are subjected to rotation transformation, the center line of the insulator in the images is in the vertical direction, and the insulator is subjected to image graying, contrast enhancement and denoising in sequence, and the method comprises the following sub-steps of,
step 1.1: graying the insulator image;
step 1.2: enhancing the contrast of the insulator image;
step 1.3: and denoising the insulator image.
3. The Canny operator-based insulator crack detection method based on maximum entropy threshold optimization according to claim 2, wherein in step 1.2, the contrast of the insulator image is enhanced, the gray scale distribution function of the image before enhancement is f (x, y), the gray scale distribution range of image pixels is [ a, b ], after the contrast of the insulator image is enhanced, the gray scale distribution range of the image pixels is [0,255], and the expression of the gray scale distribution function g (x, y) is as follows
4. The Canny operator-based insulator crack detection method based on the maximum entropy threshold optimization is characterized in that in the step 6, the crack detection is carried out on the insulator edge image possibly containing cracks, and the method comprises the following steps,
step 6.1: judging the insulator contour line which accords with the shape characteristic of the slope function in the edge curve of the edge image in the step 5, and determining an insulator region in the image;
step 6.2: and judging whether a curve spanning the adjacent umbrella skirt exists in the insulation sub-region, and if so, judging that the umbrella skirt is cracked.
5. The Canny operator based maximum entropy threshold optimized insulator crack detection method according to any one of claims 1-4, wherein the insulator image is denoised by a wiener filter.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010033618.3A CN111242923A (en) | 2020-01-13 | 2020-01-13 | Canny operator-based insulator crack detection method based on maximum entropy threshold optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010033618.3A CN111242923A (en) | 2020-01-13 | 2020-01-13 | Canny operator-based insulator crack detection method based on maximum entropy threshold optimization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111242923A true CN111242923A (en) | 2020-06-05 |
Family
ID=70870918
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010033618.3A Pending CN111242923A (en) | 2020-01-13 | 2020-01-13 | Canny operator-based insulator crack detection method based on maximum entropy threshold optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111242923A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114359156A (en) * | 2021-12-07 | 2022-04-15 | 国网湖北省电力有限公司宜昌供电公司 | Insulator string-dropping fault detection method based on image recognition |
| CN114359023A (en) * | 2022-01-10 | 2022-04-15 | 成都智元汇信息技术股份有限公司 | Method, equipment and system for dispatching picture stream to center based on complexity |
| CN114862849A (en) * | 2022-07-06 | 2022-08-05 | 山东智领新材料有限公司 | Aluminum alloy plate film coating effect evaluation method based on image processing |
| CN115830021A (en) * | 2023-02-15 | 2023-03-21 | 东莞市新通电子设备有限公司 | Metal surface defect detection method for hardware processing |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102508110A (en) * | 2011-10-10 | 2012-06-20 | 上海大学 | Texture-based insulator fault diagnostic method |
| CN103149215A (en) * | 2013-02-27 | 2013-06-12 | 中国计量学院 | Method and device for detecting defects of toughened glass insulator |
| CN105957088A (en) * | 2016-05-12 | 2016-09-21 | 广东电网有限责任公司云浮供电局 | Method and system for monitoring transformer composite insulator sleeve based on computer vision |
| CN106446905A (en) * | 2016-07-25 | 2017-02-22 | 广东省自动化研究所 | Surface crack texture extraction method based on fusion of seepage algorithm and adaptive Canny algorithm |
| CN107452007A (en) * | 2017-07-05 | 2017-12-08 | 国网河南省电力公司 | A kind of visible ray insulator method for detecting image edge |
| CN108765373A (en) * | 2018-04-26 | 2018-11-06 | 西安工程大学 | A kind of insulator exception automatic testing method based on integrated classifier on-line study |
| CN109035237A (en) * | 2018-07-31 | 2018-12-18 | 南京邮电大学 | A kind of fan blade crack detection method |
| CN109410230A (en) * | 2018-09-07 | 2019-03-01 | 南京航空航天大学 | One kind can antimierophonic improvement Canny method for detecting image edge |
| CN110455827A (en) * | 2019-08-13 | 2019-11-15 | 高瑶 | A kind of smart new energy solar panel qualification detection system and method |
-
2020
- 2020-01-13 CN CN202010033618.3A patent/CN111242923A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102508110A (en) * | 2011-10-10 | 2012-06-20 | 上海大学 | Texture-based insulator fault diagnostic method |
| CN103149215A (en) * | 2013-02-27 | 2013-06-12 | 中国计量学院 | Method and device for detecting defects of toughened glass insulator |
| CN105957088A (en) * | 2016-05-12 | 2016-09-21 | 广东电网有限责任公司云浮供电局 | Method and system for monitoring transformer composite insulator sleeve based on computer vision |
| CN106446905A (en) * | 2016-07-25 | 2017-02-22 | 广东省自动化研究所 | Surface crack texture extraction method based on fusion of seepage algorithm and adaptive Canny algorithm |
| CN107452007A (en) * | 2017-07-05 | 2017-12-08 | 国网河南省电力公司 | A kind of visible ray insulator method for detecting image edge |
| CN108765373A (en) * | 2018-04-26 | 2018-11-06 | 西安工程大学 | A kind of insulator exception automatic testing method based on integrated classifier on-line study |
| CN109035237A (en) * | 2018-07-31 | 2018-12-18 | 南京邮电大学 | A kind of fan blade crack detection method |
| CN109410230A (en) * | 2018-09-07 | 2019-03-01 | 南京航空航天大学 | One kind can antimierophonic improvement Canny method for detecting image edge |
| CN110455827A (en) * | 2019-08-13 | 2019-11-15 | 高瑶 | A kind of smart new energy solar panel qualification detection system and method |
Non-Patent Citations (1)
| Title |
|---|
| 孙晋: "基于边缘检测的绝缘子裂纹诊断研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114359156A (en) * | 2021-12-07 | 2022-04-15 | 国网湖北省电力有限公司宜昌供电公司 | Insulator string-dropping fault detection method based on image recognition |
| CN114359023A (en) * | 2022-01-10 | 2022-04-15 | 成都智元汇信息技术股份有限公司 | Method, equipment and system for dispatching picture stream to center based on complexity |
| CN114359023B (en) * | 2022-01-10 | 2022-11-18 | 成都智元汇信息技术股份有限公司 | Method, equipment and system for dispatching picture shunt to center based on complexity |
| CN114862849A (en) * | 2022-07-06 | 2022-08-05 | 山东智领新材料有限公司 | Aluminum alloy plate film coating effect evaluation method based on image processing |
| CN114862849B (en) * | 2022-07-06 | 2022-09-20 | 山东智领新材料有限公司 | Aluminum alloy plate film coating effect evaluation method based on image processing |
| CN115830021A (en) * | 2023-02-15 | 2023-03-21 | 东莞市新通电子设备有限公司 | Metal surface defect detection method for hardware processing |
| CN115830021B (en) * | 2023-02-15 | 2023-04-21 | 东莞市新通电子设备有限公司 | Metal surface defect detection method for hardware machining |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111242923A (en) | Canny operator-based insulator crack detection method based on maximum entropy threshold optimization | |
| CN113538433B (en) | Mechanical casting defect detection method and system based on artificial intelligence | |
| CN109785285B (en) | Insulator damage detection method based on ellipse characteristic fitting | |
| CN111260616A (en) | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization | |
| CN106683075B (en) | Method for detecting bolt defects at cross arm of power transmission line tower | |
| CN107730527B (en) | Remote sensing satellite image-based plateau region ice lake extraction method | |
| CN103442209B (en) | Video monitoring method of electric transmission line | |
| CN109191432B (en) | Remote sensing image cloud detection method based on domain transformation filtering multi-scale decomposition | |
| CN106709426B (en) | Ship target detection method based on infrared remote sensing image | |
| CN107506768A (en) | A kind of stranded recognition methods of transmission line wire based on full convolutional neural networks | |
| CN106157323B (en) | A kind of insulator division and extracting method of dynamic division threshold value and block search combination | |
| CN108257138B (en) | Porcelain insulator crack characteristic detection method based on edge detection | |
| CN109685766A (en) | A kind of Fabric Defect detection method based on region fusion feature | |
| CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
| CN111402215B (en) | Contact net insulator state detection method based on robust principal component analysis method | |
| CN107742307A (en) | Based on the transmission line galloping feature extraction and parameters analysis method for improving frame difference method | |
| CN106705866A (en) | Visible light image-based transmission line icing detection method | |
| CN112070717B (en) | Power transmission line icing thickness detection method based on image processing | |
| CN112215085A (en) | Power transmission corridor foreign matter detection method and system based on twin network | |
| CN112258444A (en) | Elevator steel wire rope detection method | |
| CN110288571B (en) | High-speed rail contact net insulator abnormity detection method based on image processing | |
| CN110009633A (en) | A kind of detection method of surface flaw of steel rail based on reversed difference of Gaussian | |
| CN109948629B (en) | GIS equipment X-ray image fault detection method based on SIFT features | |
| CN109272484B (en) | Rainfall detection method based on video image | |
| CN108389191B (en) | Method for detecting target shadow region in SAR image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200605 |